mannix/llama-3.3:iq3

mannix/

llama-3.3:iq3_xs

282 Downloads Updated 9 months ago

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model. I-Quants models.

tools

Updated 9 months ago

9 months ago

553e7a8d910a · 29GB ·

archllama

parameters70.6B

quantizationIQ3_XS

29GB

LLAMA 3.3 COMMUNITY LICENSE AGREEMENT Llama 3.3 Version Release Date: December 6, 2024 “Agreement�

7.6kB

Llama 3.3 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and fe

5.6kB

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"

96B

{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .System }} {{ .System }

1.5kB

Quantization from fp32
Using i-matrix calibration dataset calibration_datav3.txt
I-Quants models, only if passing tests iq2_xs, iq2_xxs, iq3_xxs, iq4_nl, iq3_s, iq2_s, iq4_xs, iq3_xs
Default quantization iq4_nl

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.